The algorithm adopts Mel frequency cepstrum coefficients (MFCC), which has lower space complexity than Bark spectrum, as feature representations for speech samples.

 
  • 该算法采用12阶美尔倒谱参数(MFCC)作为语音信号特征向量,其空间复杂度小于巴克谱。
今日热词
目录 附录 查词历史